most citedHumanity's Last Exam

18 citations

7 papers

cs.RO20261 cited

A Survey on Deep Multi-Task Learning in Connected Autonomous Vehicles

Jiayuan Wang, Farhad Pourpanah, Q. M. Jonathan Wu +1

Connected autonomous vehicles (CAVs) must simultaneously perform multiple tasks, such as perception, prediction, planning, and control, to ensure safe and reliable navigation in co…

math.CO2026

North-East Lattice Paths Avoiding Collinear Points via Satisfiability

Aaron Barnoff, Curtis Bright

We investigate the Gerver-Ramsey collinearity problem of determining the maximum number of points in a north-east lattice path without collinear points. Using a satisfiability…

cs.LG20261 cited

TIJERE: A Novel Threat Intelligence Joint Extraction Model Based on Analyst Expert Knowledge

Inoussa Mouiche, Sherif Saad

The extraction of entities and relationships from threat intelligence reports into structured formats, such as cybersecurity knowledge graphs, is essential for automated threat ana…

cond-mat.str-el2026

Finite-Size Spectral Signatures of Order by Quantum Disorder: A Perspective from Anderson's Tower of States

Subhankar Khatua, Griffin C. Howson, Michel J. P. Gingras +1

In frustrated magnetic systems with a subextensive number of classical ground states, quantum zero-point fluctuations can select a unique long-range ordered state, a celebrated phe…

cs.LG202618 cited

Humanity's Last Exam

Long Phan, Alice Gatti, Ziwen Han +1144

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…

math.CO2026

Myrvold's Results on Orthogonal Triples of Latin Squares: A SAT Investigation

Curtis Bright, Amadou Keita, Brett Stevens

Ever since E. T. Parker constructed an orthogonal pair of Latin squares in 1959, an orthogonal triple of Latin squares has been one of the most sought-aft…